vllm-project/tpu-inference

[Feature]: Add embedding model functionality to tpu-inference

Open

#899 opened on Oct 20, 2025

View on GitHub
 (6 comments) (0 reactions) (0 assignees)Python (205 forks)github user discovery
enhancementgood first issuehelp wanted

Repository metrics

Stars
 (348 stars)
PR merge metrics
 (PR metrics pending)

Description

🚀 The feature, motivation and pitch

copied from feature request in vllm upstream

Great first issue!

Should enable for both torchax and jax (if needed).

Alternatives

No response

Additional context

No response

Before submitting a new issue...

  • Make sure you already searched for relevant issues, and asked the chatbot living at the bottom right corner of the documentation page, which can answer lots of frequently asked questions.

Contributor guide

Research direction
Study how vLLM implements embedding models and adapt the TPU backend to support them. Look at the existing inference pipeline and add a new endpoint or mode for embeddings. Start by reading the vLLM documentation on embedding models and examining the current TPU inference code to understand where to add the functionality.
Tech stack
pythonpytorch
Domain
aibackend
Issue type
Feature
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
1
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
1-3 hours
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
Active
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
Clear
Prerequisites
PythonGitPyTorch
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
80